Tribalscale AI Engineer at TribalScale responsible for building and operating AI agent infrastructure and workflows. The role includes developing CI/CD pipelines, managing AI gateways, and instrumenting AI pipelines for performance and reliability.
Responsibilities
We are looking for a talented and driven developer to join a client of TribalScale's team and build the shared, cloud native agent infrastructure on AWS that our AI-assisted modeling pipeline and our internal AI-enabled development workflow run on. A client of TribalScale, builds virtual Arm devices: phones, IoT boards and automotive controllers that run real, unmodified firmware on a client of TribalScale’s CHARM hypervisor. Atlas is our product for virtual IoT, automotive and embedded hardware. Today each new device model takes a team of modeling engineers weeks of reading reference manuals and hand-writing peripheral models. We are building an AI-assisted modeling pipeline that collects vendor documentation, extracts per-peripheral specifications, generates register and system definitions, synthesizes behavioral C code, and validates the result by booting vendor firmware. We use it on our own bring-ups first, then hand it to Atlas partners so they can build and validate their own models.
This role sits on our AI & SDLC Platform team, which supplies agent infrastructure and AI platform support to the delivery teams. Model Delivery owns the modeling backlog and its outcomes. You own the substrate that pipeline runs on: job orchestration, multi-model inference, evaluation hooks, observability and secure deployment. Your work takes the pipeline from an engineer-run prototype to a reliable, measured service. You apply the same infrastructure to replace parts of our internal software development process with AI-enabled workflows.
Design and implement orchestration for long-running agent pipelines on AWS: job orchestration, artifact and manifest generation, checkpointing, retries, and prompt and model versioning.
Run multi-model inference across Amazon Bedrock and self-hosted models, with routing, an independent judge model, semantic caching and token-cost and latency controls.
Provide shared evaluation and tracing hooks so Model Delivery can measure each pipeline stage and compare models, prompts and pipeline versions.
Build and operate the internal AI gateway, agent runtime and tool integrations that engineers use in the AI enabled SDLC: code review, ticket-to-merge-request workflows and knowledge retrieval.
Develop and maintain CI/CD pipelines and infrastructure as code (Terraform or CDK) with secure secrets management and least-privilege access.
Instrument agents and pipelines (success rate, cost, latency, failure modes) and maintain dashboards, alerts and runbooks.
Work with the product teams that own customer-facing MCP and API surfaces so internal agent tools and product interfaces stay consistent.
Hands-on experience with AWS services including Bedrock, Lambda, ECS or EKS, S3 and Step Functions.
Experience with GenAI infrastructure: LLM integration, agent frameworks, MCP, semantic caching and LLM evaluation.
Familiarity with Amazon EKS and Kubernetes-based deployments.
Qualification
Ability to write cleanHigh degree of ownershipExperience with Agentic AI FrameworksAdvanced AWS ExperienceMulti-Model LLM ExperienceAI-Assisted Development ToolsLLM Evaluation & ObservabilityEmbedded Systems & VirtualizationModel Context Protocol (MCP)Infrastructure Scalability
Required
Hands-on experience with AWS services including Bedrock, Lambda, ECS or EKS, S3 and Step Functions
Experience with GenAI infrastructure including LLM integration and agent frameworks
Familiarity with Amazon EKS and Kubernetes-based deployments
Familiarity with GitHub/GitLab workflows and secure deployment practices
Knowledge of observability tools like Datadog and log aggregation strategies
Ability to write clean, maintainable code and contribute to documentation
Experience collaborating with customers and cross-functional teams
Excellent written and verbal communication skills
Comfort working in fast-moving environments
High degree of ownership, curiosity, empathy, and bias toward action
Ability to travel occasionally for client workshops or on-site delivery
Preferred
Experience with Agentic AI Frameworks: Hands-on experience with LangChain, LangGraph, CrewAI, AutoGen, or similar frameworks for building and orchestrating AI agents.
Advanced AWS Experience: Experience optimizing AI workloads using Amazon Bedrock, SageMaker, or other AWS AI/ML services.
Multi-Model LLM Experience: Experience integrating and managing multiple LLM providers, including OpenAI, Anthropic Claude, and open-source models.
AI-Assisted Development Tools: Familiarity with Claude Code, Cursor, GitHub Copilot, or similar AI-powered development tools.
LLM Evaluation & Observability: Experience with tools such as LangSmith, Langfuse, Arize Phoenix, or similar platforms for monitoring and evaluating AI systems.
Embedded Systems & Virtualization: Exposure to Arm architectures, firmware development, IoT devices, hypervisors, or hardware virtualization.
Model Context Protocol (MCP): Experience building MCP servers, integrating external tools, or developing reusable agent tooling.
Infrastructure Scalability: Experience with distributed systems, Kubernetes, container orchestration, and scaling production AI workloads.